Delay-dependent H ∞ and generalized H 2 filtering for stochastic neural networks with time-varying delay and noise disturbance

Hua, Mingang; Tan, Huasheng; Chen, Junfeng

doi:10.1007/s00521-013-1531-7

Cited by 16 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Remarkmentioning

confidence: 99%

“…The filter discussed in this paper of the form (9) and (10) is the same as that in [13,47,52]. As pointed out in [13], the signal zðtÞ of the filter depends on C f , which is to be determined. However, there doesn't exist C f to estimate signal z m ðtÞ and z p ðtÞ in [6,24,26,36,41,43,50].…”

Section: Remarkmentioning

confidence: 99%

“…The neural networks studied in [1,6,13,14,24,26,36,41,43,46,50,52] don't include any analysis of neutral phenomena. Although the neutral phenomenon has been investigated in [19], the results in [19] are obtained in deterministic setting rather than stochastic setting.…”

Section: Remarkmentioning

confidence: 99%

“…Therefore, the stochastic disturbance of neural networks was taken into account in [13, 24, 26, 29, 36, 39-41, 50, 52]. For example, delay-dependent H 1 and generalized H 2 filtering for delayed neural networks in deterministic setting and stochastic setting were studied in [14] and [13], respectively. Robust H 1 filter design for a class of stochastic Markovian jump Hopfield neural networks with mode-dependent time-varying delays and norm-bounded parameter uncertainties was addressed in [52].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust stability and $$H_{\infty}$$ H ∞ filter design for neutral stochastic neural networks with parameter uncertainties and time-varying delay

Hua

Tan

Fei

et al. 2015

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

This paper is concerned with the problem of robust stability and H 1 filter design for neutral stochastic neural networks with parameter uncertainties and timevarying delay. The parameter uncertainties are assumed to be norm-bounded. With the Lyapunov-krasovskii theory, several delay-dependent stability conditions are obtained in terms of liner matrix inequalities(LMIs). Based on the obtained stability criteria, some sufficient conditions for the existence of the robust H 1 filter are derived. The obtained results ensure the robust stability and a prescribed H 1 performance level of the filtering error systems for all admissible uncertainties. Finally, two numerical examples are given. One is provided to demonstrate the stability analysis results in this paper are less conservative than some existing results. The other is provided to illustrate the effectiveness of the filter design method.

show abstract

Section: Remarkmentioning

confidence: 99%

Section: Remarkmentioning

confidence: 99%

Section: Remarkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust stability and $$H_{\infty}$$ H ∞ filter design for neutral stochastic neural networks with parameter uncertainties and time-varying delay

Hua

Tan

Fei

et al. 2015

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since it contains two gain matrices, the Arcak-type filter is regarded as an extension of the Luenberger-type filter. In addition, another generalized 2 full-order filter was designed for a class of delayed stochastic NNs in [11], in which three gain matrices were involved.…”

Section: Introductionmentioning

confidence: 99%

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper focuses on the generalized 2 filtering of static neural networks with a time-varying delay. The aim of this problem is to design a full-order filter such that the filtering error system is globally asymptotically stable with guaranteed 2 performance index. By constructing an augmented Lyapunov-Krasovskii functional and applying the free-matrix-based integral inequality to estimate its derivative, an improved delay-dependent condition for the generalized 2 filtering problem is established in terms of LMIs. Finally, a numerical example is presented to show the effectiveness of the proposed method.

show abstract

Improved Results on Guaranteed Generalized $${\mathcal {H}}_{2}$$ H 2 Performance State Estimation for Delayed Static Neural Networks

Shu

Liu

et al. 2016

Circuits Syst Signal Process

View full text Add to dashboard Cite

Delay-dependent H ∞ and generalized H 2 filtering for stochastic neural networks with time-varying delay and noise disturbance

Cited by 16 publications

References 40 publications

Robust stability and $$H_{\infty}$$ H ∞ filter design for neutral stochastic neural networks with parameter uncertainties and time-varying delay

Robust stability and $$H_{\infty}$$ H ∞ filter design for neutral stochastic neural networks with parameter uncertainties and time-varying delay

Improved GeneralizedH2Filtering for Static Neural Networks with Time-Varying Delay via Free-Matrix-Based Integral Inequality

Improved Results on Guaranteed Generalized $${\mathcal {H}}_{2}$$ H 2 Performance State Estimation for Delayed Static Neural Networks

Contact Info

Product

Resources

About